Find answers from the community

Updated 3 months ago

hi guys I am creating a new query engine

hi guys. I am creating a new query engine with csv data. I create a custom document with a metadata keyword.
when I query with the word Parotiditis I get Parotiditis is a medical condition that is being referred to in the given context. But one node is the has the following metadata: 'bd87575f-6aca-4ebe-bbae-0320521c6ced': RefDocInfo(node_ids=['7fc5ef03-033e-479f-8c9d-7d03fab082f4'], metadata={'keyword': 'Ac IgM Parotiditis'}),
What can I do to get the info with that metadata keyword??
e
L
4 comments
this is the code I use to create the Documents:
def tranform_dataset_item(row): return Document( text=f"""El nombre del estudio es {row['nombre']}. Para este estudio se realizan {row['ayuno']} de ayuno. El tipo de muestra es {row['tipo_de_muestra']}. El documento con indicaciones más detalladas la puede encontrar a continuación: {row['pagina_indicaciones']}""", metadata={ "keyword": row["nombre"], }, )
Do you suggest any changes?
if I make the query with something more specific as the text indicaciones para estudio de Parotiditis. I get the correct answer: Las indicaciones para el estudio de Parotiditis se pueden encontrar en el siguiente documento: https://www.company.com/-Indicaciones-Generales.pdf
any ideas @Logan M ?
Yea, queries should be actual questions if you want the LLM to write a proper response 👍
Add a reply
Sign up and join the conversation on Discord